Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to political theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eid
    -0.18
    ldb
    -0.16
    NCY
    -0.15
    _ENGINE
    -0.15
    AMPL
    -0.15
    ruba
    -0.15
    omentum
    -0.14
    /Dk
    -0.14
    rub
    -0.14
    omon
    -0.14
    POSITIVE LOGITS
     IR
    0.33
    IR
    0.26
     interstate
    0.25
     Morg
    0.25
     Walt
    0.23
    (IR
    0.23
     realism
    0.22
     actors
    0.22
     state
    0.22
     security
    0.22
    Act Density 0.016%

    No Known Activations